3.0

credits

Average Course Rating

The primary objective of this course is to foster a deep and holistic comprehension of the concepts surrounding deep learning, as well as their practical applications within engineering systems. This course encompasses a broad spectrum of methodologies, notably emphasizing the utilization of physics-informed and data-driven techniques for both time-dependent and static Partial Differential Equations (PDEs) and Ordinary Differential Equations (ODEs). We delve into the study of multi-layer perceptrons, Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and autoencoders, exploring their roles in discerning patterns within data, providing solutions even in scenarios with limited data availability, and learning a family of equations using one network architecture. Through this course, students will acquire the skills to proficiently employ these methods in tackling a wide-ranging spectrum of computational challenges prevalent in domains like solid mechanics, biomechanics, and systems engineering. Proficiency in Python coding is essential for this course. To make the most of this course, it's important to have a basic understanding of Linear Algebra and Probability.